What is he best known for?
The fields of study he is best known for:
- Statistics
- Algorithm
- Mathematical analysis
Ilias Diakonikolas spends much of his time researching Combinatorics, Discrete mathematics, Algorithm, Estimator and Time complexity.
He interconnects Matching and Function in the investigation of issues within Combinatorics.
His studies deal with areas such as Simple, Distribution, Polynomial and Monotone polygon as well as Discrete mathematics.
His study explores the link between Polynomial and topics such as Boolean function that cross with problems in Representation.
His work deals with themes such as Mixture model, Logarithm, Fraction and Robustness, which intersect with Algorithm.
He has included themes like Covariance, Mathematical optimization, Upper and lower bounds, Pareto distribution and Spanning tree in his Time complexity study.
His most cited work include:
- Robust Estimators in High Dimensions without the Computational Intractability (136 citations)
- Optimal algorithms for testing closeness of discrete distributions (133 citations)
- Bounded Independence Fools Degree-2 Threshold Functions (86 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Combinatorics, Discrete mathematics, Algorithm, Upper and lower bounds and Distribution.
Ilias Diakonikolas has researched Combinatorics in several fields, including Probability distribution, Total variation, Constant, Function and Polynomial.
His Discrete mathematics research is mostly focused on the topic Boolean function.
His research in the fields of Time complexity overlaps with other disciplines such as Gaussian.
The concepts of his Upper and lower bounds study are interwoven with issues in Uniform distribution, Multivariate statistics and Domain.
His Distribution research includes elements of Property testing, Monotone polygon, Identity, Domain and Bounded function.
He most often published in these fields:
- Combinatorics (42.92%)
- Discrete mathematics (28.76%)
- Algorithm (25.32%)
What were the highlights of his more recent work (between 2019-2021)?
- Algorithm (25.32%)
- Gaussian (12.02%)
- Distribution (23.18%)
In recent papers he was focusing on the following fields of study:
Ilias Diakonikolas spends much of his time researching Algorithm, Gaussian, Distribution, Combinatorics and Outlier.
His studies in Algorithm integrate themes in fields like Fraction and Stationary point.
His work carried out in the field of Distribution brings together such families of science as Covariance, Bounded function and Approximation algorithm.
His work deals with themes such as Upper and lower bounds, Polynomial, Cover and Marginal distribution, which intersect with Combinatorics.
While the research belongs to areas of Upper and lower bounds, he spends his time largely on the problem of Exponential function, intersecting his research to questions surrounding Robustness.
Ilias Diakonikolas interconnects Estimator, Applied mathematics and Constant in the investigation of issues within Outlier.
Between 2019 and 2021, his most popular works were:
- Learning Halfspaces with Massart Noise Under Structured Distributions (12 citations)
- Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks (11 citations)
- Robustly Learning any Clusterable Mixture of Gaussians. (10 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Algorithm
- Mathematical analysis
Ilias Diakonikolas focuses on Algorithm, Gaussian, Time complexity, Square and Combinatorics.
His research in Algorithm intersects with topics in Upper and lower bounds and Stationary point.
The Upper and lower bounds study combines topics in areas such as Condition number, Matrix, Learnability and Rank.
His Stationary point research focuses on Line and how it relates to Outlier, Robust statistics and Constant.
Ilias Diakonikolas has included themes like Total variation, Explained sum of squares, Bounded function, Identifiability and Polynomial in his Constant study.
His Square research is multidisciplinary, incorporating elements of Current, Distribution and Marginal distribution.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
